In this paper, we propose a computational model of the recognition of real world scenes that bypasses the segmentation and the processing of individual objects or regions. The procedure is based on a very low dimensional representation of the scene, that we term the Spatial Envelope. We propose a set of perceptual dimensions (naturalness, openness, roughness, expansion, ruggedness) that represent the dominant spatial structure of a scene. Then, we show that these dimensions may be reliably estimated using spectral and coarsely localized information. The model generates a multidimensional space in which scenes sharing membership in semantic categories (e.g., streets, highways, coasts) are projected closed together. The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.

this article. This paper has also benefited greatly from constructive feedback from Gordon Logan, Mike Stadler, and our other reviewers. We thank Joanie Sanchez for her assistance in running Experiment 1. This research was supported by a Social Science Faculty Research Award from Yale University. Portions of this research were presented at the Annual Meeting of the Association for Research in Ophthalmology and Vision, Fort Lauderdale, FL, in May, 1997, and at the Annual Meeting of the Psychonomic Society, Philadelphia, PA, in November, 1997

The emerging viewpoint of embodied cognition holds that cognitive processes are deeply rooted in the body’s interactions with the world. This position actually houses a number of distinct claims, some of which are more controversial than others. This paper distinguishes and evaluates the following six claims: 1) cognition is situated; 2) cognition is time-pressured; 3) we off-load cognitive work onto the environment; 4) the environment is part of the cognitive system; 5) cognition is for action; 6) off-line cognition is body-based. Of these, the first three and the fifth appear to be at least partially true, and their usefulness is best evaluated in terms of the range of their applicability. The fourth claim, I argue, is deeply problematic. The sixth claim has received the least attention in the literature on embodied cognition, but it may in fact be the best documented and most powerful of the six claims.

Many experiments have shown that the human visual system makes extensive use of contextual information for facilitating object search in natural scenes. However, the question of how to formally model contextual influences is still open. On the basis of a Bayesian framework, the authors present an original approach of attentional guidance by global scene context. The model comprises 2 parallel pathways; one pathway computes local features (saliency) and the other computes global (scenecentered) features. The contextual guidance model of attention combines bottom-up saliency, scene context, and top-down mechanisms at an early stage of visual processing and predicts the image regions likely to be fixated by human observers performing natural search tasks in real-world scenes.

Change blindness is the striking failure to see large changes that normally would be noticed easily. Over the past decade this phenomenon has greatly contributed to our understanding of attention, perception, and even consciousness. The surprising extent of change blindness explains its broad appeal, but its counterintuitive nature has also engendered confusions about the kinds of inferences that legitimately follow from it. Here we discuss the legitimate and the erroneous inferences that have been drawn, and offer a set of requirements to help separate them. In doing so, we clarify the genuine contributions of change blindness research to our understanding of visual perception and awareness, and provide a glimpse of some ways in which change blindness might shape future research.

Spatial attention: Visual selection and deployment over space The attentional spotlight and spatial cueing Attentional shifts, splits, and resolution Object-based Selection The visual search paradigm Top-down and bottom-up control of attention Inhibitory mechanisms of attention Invalid cueing Negative priming Inhibition of return Temporal attention: Visual selection and deployment over time Single target search Attentional blink and attentional dwell time Repetition blindness NEURAL MECHANISMS OF SELECTION Single-cell physiological method Event-related potentials Functional imaging: PET and fMRI

When brief blank fields are placed between alternating displays of an original and a modified scene, a striking failure of perception is induced: The changes become extremely difficult to notice, even when they are large, presented repeatedly, and the observer expects them to occur (Rensink, O’Regan, & Clark, 1997). To determine the mechanisms behind this induced “change blindness”, four experiments examine its dependence on initial preview and on the nature of the interruptions used. Results support the proposal that representations at the early stages of visual processing are inherently volatile, and that focused attention is needed to stabilize them sufficiently to support the perception of change. Over the past few decades, evidence has been accumulating that—contrary to our subjective impressions—we do not have a coherent and detailed representation of the coherent and detailed world that surrounds us. For example,

Occupants of future computing environments with ubiquitous display devices may feel inundated with changing digital information. One solution is to create a reasoning module that accepts requests to display information from multiple applicatins and controls how the information is presented to minimize visual disruptions to users. Such a system might use information about what activity is occurring in the space to exploit a powerful phenomenon of the human visual system: change blindness.

Observers inspected normal, high quality colour displays of everyday visual scenes while their eye movements were recorded. A large display change occurred each time an eye blink occurred. Display changes could either involve “Central Interest” or “Marginal Interest” locations, as determined from descriptions obtained from independent judges in a prior pilot experiment. Visual salience, as determined by luminance, colour, and position of the Central and Marginal Interest changes were equalized. The results obtained were very similar to those obtained in prior experiments showing failure to detect changes occurring simultaneously with saccades, flicker, or “mudsplashes” in the visual scene: Many changes were very hard to detect, and Marginal Interest changes were harder to detect than Central Interest changes. Analysis of eye movements showed, as expected, that the probability of detecting a change depended on the eye’s distance from the change location. However a surprising finding was that both for Central and Marginal Interest changes, even when observers were directly fixating the change locations (within 1 degree), more than 40 % of the time they still failed to see the changes. It seems that looking at something does not guarantee you “see” it.

. In visual navigation, landmarks can be used in a number of different ways. In this paper we investigate the role of global and local landmarks in virtual environment navigation. We performed an experiment in a virtual environment called "Hexatown". Hexatown consists of a regular hexagonal grid of junctions joined together by streets. At each junction there are three buildings, or other objects. Additionally, we provide global direction or compass information by three distant "global landmarks" (a hilltop and a television tower at a mountain range, and a skyline of a distant city). Participants navigated in Hexatown by pressing the buttons of a computer mouse. According to their movement decisions, egomotion was simulated. Participants had to learn the route back and forth between two specific buildings. In the test-phase individual junctions were approached and the participants' movement decision was recorded. We performed two experiments with the same task but different paradigms. I...